Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2789
    Prev
    Next
    INDEX
    Explanations

    phrases related to improving relationships and business collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.48
     Iden
    -0.46
     noqa
    -0.45
     Arbe
    -0.42
     hoş
    -0.42
    ngdoc
    -0.40
    CommonModule
    -0.40
     يتيمه
    -0.40
    ırl
    -0.40
     Trace
    -0.39
    POSITIVE LOGITS
     level
    1.15
     levels
    0.97
    level
    0.93
     LEVEL
    0.92
     another
    0.91
     Level
    0.88
    LEVEL
    0.87
    Level
    0.86
     notches
    0.86
    レベル
    0.82
    Activations Density 0.119%

    No Known Activations